© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219253
    Prev
    Next
    INDEX
    Explanations

    future customers

    np_acts-logits-general · gemini-2.5-flash-lite

    fibonacci sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ដែល
    0.45
     及
    0.44
     до
    0.43
     ਡ
    0.43
     які
    0.43
     ลักษณะ
    0.43
     তাড়াতাড়ি
    0.43
    Ibid
    0.42
     ಯು
    0.42
    及其
    0.41
    POSITIVE LOGITS
     emphatic
    0.56
    ING
    0.52
     kindred
    0.51
    ي
    0.50
     kinship
    0.50
    owment
    0.50
     reagent
    0.49
     dissent
    0.48
     envoy
    0.48
    ക
    0.48
    Activations Density 0.000%

    No Known Activations